论文信息 - Efficient motion sensing algorithm for camera-enabled mobile devices

Efficient motion sensing algorithm for camera-enabled mobile devices

In this paper we present an efficient motion sensing algorithm for camera-enabled mobile device. In our algorithm, we first perform colour space acquisition to extract red colour component from ARBG colour space before applying motion estimation. Full-search block matching algorithm (FBMA) is used for motion estimation due to its simplicity for mobile environment. After getting the estimated motion vector, we then perform a future motion prediction in order to produce a better and smoother motion output. Finally, we implemented and tested our algorithm on the Nokia N73 phone using Java J2ME programming language.

Yoong Choon Chang | Kok Chen Lim | T. Kian

[1] Vidya Setlur,et al. Camera-Based Virtual Environment Interaction on Mobile Devices , 2006, ISCIS.

[2] Eric Horvitz,et al. Sensing techniques for mobile interaction , 2000, UIST '00.

[3] Berthold K. P. Horn,et al. Determining Optical Flow , 1981, Other Conferences.

[4] Xu Liu,et al. Fast camera motion estimation for hand-held devices and applications , 2005, MUM '05.

[5] Paul A. Beardsley,et al. Computer Vision for Interactive Computer Graphics , 1998, IEEE Computer Graphics and Applications.

[6] Jun Rekimoto,et al. Tilting operations for small screen interfaces , 1996, UIST '96.

[7] Roy Want,et al. Squeeze me, hold me, tilt me! An exploration of manipulative user interfaces , 1998, CHI.

[8] Ka-Ping Yee,et al. Peephole displays: pen interaction on spatially aware handheld computers , 2003, CHI '03.

[9] Shumin Zhai,et al. Camera phone based motion sensing: interaction techniques, applications and performance study , 2006, UIST.

[10] Janne Heikkilä,et al. A Vision-Based Approach for Controlling User Interfaces of Mobile Devices , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.